Xcavator.net is a stock photo search portal based on visual search technology.
Xcavator.net provides natural and intuitive interactive search for stock photography providing buyers with a browsing experience based on both visual content and keywords. The key to the visual search capabilities is the portal’s color and image search engines, powered by CogniSign Intelligent Image Recognition Technology.
In laymen’s terms, Xcavator.net offers three types of interrelated search options. Tradition search delivers photos based on tagged keywords and is much the same as others in the stock photography market. Where Xcavator.net gets interesting is in color and image search. Xcavator.net allows color search matching, for example if a stock photograph was needed that matched a brochure or web site in terms of colors, users are able to refine the photo search to those colors by utilizing a color chart or by inserting the exact hexadecimal color into a box. Image search provides similar photos based on a user uploaded image or via a drag and drop of images found in an initial search.
Xcavator.net competes with other visual search sites including Riya, Pixsy and PicSearch. Xcavator isn’t necessarily better than any of their competitors, but different. The color and related search capabilities don’t have the same level of user enjoyment as Riya’s search features do, yet Xcavator.net’s features feel more practical and are definitely more finely targeted at niche stock photo search.
Xcavator.net recently signed a deal with iStockphoto that delivers 1.8 Million images from 38,000 contributors into the Xcavator.net search database. The site comes out of Beta on July 2.
Yeah, these kinds of services have a ton of room for improvement. Reminds me of product suggestion, it’s one of those things that see,s like it could be so much better but has been sort of stagnant for years.
The color search isn’t revolutionary, but it is nice, and useful. One more player here at least directs more attention to the problem and increases the chances of bigger improvements.
Sweet! 10 minute load times. I’m sure that will work perfect for most people looking to skim through stock photography.
Cool. I’m really into visual search for a project i’m working on related to a non profit. I am glad to find more sources for this. Right now, the real stuff is still, I guess, at the research/university level and it has a long way to go, but the ability to do it effectively could change a lot of things in the world.
yay, duncan! great article!
Brent
I didn’t have any issues with load time, and given my distance (literally the other side of the world to the US) and crappy 2mb internet connection I’m sure I would have noticed
Sounds like the next big thing. Is this going to be funded by Sequoia or by DFJ?
Man alive you sure this isn’t a secret attempt by Jerry Yang to incorporate flickers back end into a new face. I am seeing alot of similarities.
Either or I am seeing huge lag times when loading which means some people are actually using it unlike flickers or there is a lack of bandwidth or the standard 200 ports a second default connection limitation needs to be removed … Duhhh either or I like it just its so dam slow.
Great idea and executed very well.
there is loads of stock photography sites. i like real photos from getty images etc.
Brent is right, the site doesn’t load.
I have been working on a similar content-based image search engine that indexes images from one of the Flickr groups (and also from the WWW). What makes it different from search engines like Xcavator or Riya is that you can *verbally* specify what the photos should actually look like, rather than just choosing colour or looking for similar images. E.g. “find pictures tagged with london that *look* like images of buildings” (where the images do not necessarily need to be tagged with ‘building’ to be found).
Video demos of how it works are here.
And the search engine itself is here.
I would really appreciate your feedback on this early technology. Thanks!
Alexei
I made a post about this site yesterday: http://www.techcrunch.com/2007.....to-search/
Cool and great. Got also a problem to load the site.
yeah loads slow as hell ;
- too many competitors /
- and the site is generally weak.
We’ve had incredible traffic from this posting and other blog postings, and are experiencing some site problems. Please keep in mind we are in BETA. We’ll be working through these as quickly as we can. The site gives a fantastic experience when working well. Thanks to all for your patience and interest.
The problem is: Xcavator searches images in Photovault’s database which is not really cool, since each one of those images cost a fortune. Too bad. What’s the point then? I want to be able to download those images for free. Integrate more site, not just Photovault. Not that I’m not willing to pay, but $50 per image seems absurd to me. Bad idea, Xcavator folks.
Ouch….on the site problems. Seeing a lot of startups really not thinking through their network architecture before putting themselves out there.
Getting a write-up on Techcrunch is important….and should be able to handle the attention. Hard to have a redo on first impressions and this crowd is tough.
Interesting search implementation though…we’ll see.
our site sucks, but hey we’re in beta. It’ll be good in a couple of years. Honest it will.
I’m posting to let everyone know our site has been reconfigured to handle the kind of load it received last week from this Techcrunch posting (and other blog postings at the same time). Please accept my sincere apologies for the problems.
xcavator.net is a fantastic visual browsing experience when working properly, as it is now. I urge all of you to check it out again. Responding to complaints about our company not preparing properly for a Techcrunch blog posting; well, we certainly tried. However, it is a very sophisticated site and we do not currently have automated testing systems in place to put it under the heavy load it experienced last week. Someday before too long we will have them.
Thanks, Duncan, for a great review.